JP2005352694A - Printing device, printing method, information processing device, and control method thereof - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem that electric power is wastefully consumed by a part unnecessary for distributed processing if equipment, to which distributed processing is made, is restored to a normal operational state for executing distributed processing in case that the equipment is in a power-saving mode. <P>SOLUTION: A computer device, which has an electric power restraint part which stops the supply of electric power or clock to a part of modules constituting a device or reduces a clock frequency, determines the kind of a packet received from a host machine via a computer network (S701-S703). When the result of the determination indicates the reception of a packet indicating the start of distributed processing, the computer device releases clock stop and performs clock-up only to resources necessary for the distributed processing only (S705). <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an information processing apparatus and a control method thereof, for example, to a case where a load distribution system of grid computing is applied to an information processing apparatus such as a printer or a multi-function printing apparatus connected to a computer network.

  FIG. 1 is a diagram for explaining the architecture of grid computing. Although there are several types of grids, what is described here is a type called a desktop grid that executes jobs using the free time of a CPU such as a desktop PC.

  The client PC shown in FIG. 1 submits a job according to the user's instruction (S1), the request (job) is passed to the task manager (hereinafter abbreviated as “TM”), and the TM is its contents (job (Request) is transmitted to the Dynamic Job Scheduler (hereinafter referred to as “DJS”) (S2). The DJS that manages the resources of the entire grid computing system selects the optimal resource broker and notifies the TM (S3). Here, the resource means a free state of the PC CPU.

  The broker in the PC also registers the information on the resources that the resource manager (hereinafter abbreviated as “RM”) in the PC with DJS. When a request is received from the TM (S4), a job is submitted to the RM (S5), and the completion (and processing result) of the job is notified to the TM (S6). After submitting a job to the broker selected by DJS, TM monitors the progress of the job, receives a completion notification (and processing result) from the broker (S6), and notifies the client PC of the completion notification (and processing). (Result) is notified (S7).

  In addition, the RM notifies the broker of resource information, and submits a job to the resource according to an instruction from the broker. Further, the state of the resource is periodically checked, and if there is a change / abnormality in the resource (for example, a failure or another job is accepted), the broker is notified of this.

  With this mechanism, the realization of desktop grid computing is to enable distributed processing by allocating jobs to optimal (not normally used) resources such as CPUs.

  On the other hand, there is a case where the device is in the power saving mode, power is not supplied to some modules of the device, or the operating frequency (for example, CPU clock frequency) is low. In order to return the devices in the power saving state to the normal operation state, there is a method of causing the devices to receive a specific packet called a magic packet. However, in the case of a device subject to distributed processing as described above, if the device is returned to a normal operation state for distributed processing, a portion (module) unnecessary for distributed processing consumes useless power.

  In addition, when printing a large number of pages and copies, there are multiple proposals for clustering mechanisms that enable high-speed printing by dividing the output destination (distributed printing), and devices on the network (printers and multifunction printers) Etc.) is distributed to other devices connected to the network to distribute the processing, thereby completing the processing at high speed. However, this distributed processing divides a page to be printed and the number of copies and allows a plurality of devices to perform printing, and the device designated by the client does not print all pages and the number of copies.

  On the other hand, if the load distribution system of grid computing is applied to the above devices, the data processing and image processing for printing are distributed to these devices, and the devices designated as clients are all based on the processing results. Printing pages and copies can be performed. In other words, a client user can obtain a desired print result in a short time from a designated device without being conscious of distributed processing.

IBM Professional Paper “Applicability of Grid Computing to Commercial Systems” http://www-6.ibm.com/jp/provision/no36/pdf/36_ppr1.pdf

  The present invention solves the above-mentioned problems individually or collectively, and an object of the present invention is to suppress power consumption when a target device of distributed processing performs distributed processing.

  The present invention has the following configuration as one means for achieving the above object.

  The present invention is an information processing apparatus connected to a computer network, and when a packet indicating distributed processing is received from a host machine via the computer network, only the resources necessary for the distributed processing are canceled and the clock is released. It is characterized by performing up.

  Further, in an information processing apparatus connected to a computer network, when receiving a packet indicating distributed processing from a host machine via the computer network, supply of a clock to a resource unnecessary for the distributed processing is stopped. Alternatively, the frequency of the clock supplied to the resource is set to a frequency lower than that during normal operation.

  In addition, when the information processing apparatus is connected to a computer network and the information processing apparatus is not performing data processing, power or a clock supplied to some modules constituting the information processing apparatus is stopped. Alternatively, power suppression means for reducing the frequency of the clock, determination means for determining the type of a packet received from a host machine via the computer network, and reception of a packet whose determination result indicates the start of distributed processing In this case, the power supply or the clock supplied to the modules required for the distributed processing is stopped, and the control means for canceling the reduction of the clock frequency is included.

  An information processing apparatus connected to a computer network, wherein the information processing apparatus includes: a receiving unit that receives a packet from a host machine via the computer network; and the information processing apparatus is not performing data processing. The power supply to a part of the modules constituting the power supply is stopped, and when the receiving means receives the packet, the power suppression means for canceling the suspension of the power supply and the part of the modules constituting the information processing apparatus are supplied. The clock control means for stopping the clock or reducing the frequency of the clock and the type of the packet received by the receiving means are determined, and when the packet indicates the start of distributed processing, the distribution to the clock control means Stop the clock supplied to modules not required for processing, or reduce the frequency of the clock And having a control means for causing.

  An information processing apparatus connected to a computer network, wherein the data in the area allocated to the memory is saved in a storage device, and the save / return means for restoring the data saved in the storage device to the memory; and the information Clock control means for stopping the clock supplied to some modules constituting the processing device or reducing the frequency of the clock, and determination means for determining the type of packet received from the host machine via the computer network When the determination result indicates reception of a packet indicating the start of distributed processing, the save / restore means saves data in a predetermined area on the memory, and the clock control means moves to a module unnecessary for the distributed processing. Control means for stopping the clock to be supplied or reducing the frequency of the clock It is characterized in.

  When the control method of the present invention is connected to a computer network and the apparatus is not processing data, the power or clock supplied to some modules constituting the apparatus is stopped, or the frequency of the clock is set. A method of controlling an information processing apparatus having a power suppression unit that reduces a type of a packet received from a host machine via the computer network, and receives a packet whose determination result indicates the start of distributed processing. In the case shown, the stop of the power or clock supplied to the modules necessary for the distributed processing and the reduction of the frequency of the clock are cancelled.

  In addition, a receiving unit that is connected to a computer network and receives a packet from a host machine via the computer network, and a power supply to some modules constituting the device when the device is not processing data The information processing apparatus has a power suppression unit that cancels the stop of power supply when the receiving unit receives a packet, and determines the type of packet received by the receiving unit, Indicates the start of distributed processing, the clock supplied to the module unnecessary for the distributed processing is stopped, or the frequency of the clock is reduced.

  A method of controlling an information processing apparatus connected to a computer network, wherein the type of packet received from a host machine via the computer network is determined, and reception of a packet whose determination result indicates the start of distributed processing , The data in a predetermined area in the memory is saved in a storage device, and the clock supplied to the module unnecessary for the distributed processing is stopped or the frequency of the clock is reduced.

  According to the present invention, it is possible to suppress power consumption when a target device of distributed processing performs distributed processing.

  Hereinafter, an embodiment suitable for the present invention will be described in detail with reference to the drawings.

[Overview]
FIG. 2 is a diagram illustrating a configuration example in the case of applying desktop grid computing technology to printer description language (PDL) processing. In the description of FIG. 1, each module constituting the grid is treated as a separate one. However, when the desktop grid computing technology is applied to a printing apparatus, it is common that a plurality of modules exist in one device. It seems to be the target.

  The client PC 901 in FIG. 2 instructs the printer 902 to perform printing (input a print job). The printer 902 has TM and DJS functions (that is, a host machine for distributed processing), and the PCs 903 to 905 have broker and RM functions. With this configuration, for example, distributed processing by grid computing using three PCs connected to the network 907 becomes possible.

  A job (print job of data in PDL format) submitted from the client PC 901 is, for example, the first page to the PC 903, the second page to the PC 904, the third page by the TM and DJS of the printer 902 as the host machine. The page is distributed to each resource such as to the PC 905, and the development process from PDL data to image data is executed. At this time, an application program for image development processing of PDL data is also simultaneously transmitted from the printer 902 to each resource. The images developed from the PDL data by each PC (that is, the processing results of the first to third page images) are collected by the printer 902 which is the host machine, and the three-page image 906 is printed out. The client PC 901 is notified of the end of printing.

  Of course, the target resource of this distributed processing may be four or more PCs, the resource of the client PC 901 of the job submission source can be used, and the resources of other printers on the network 905 are targeted. May be.

  However, as described above, there are cases where the device has entered the power saving mode, power is not being supplied to some modules of the device, or the operating frequency (for example, the CPU clock frequency) is low. is there. If these devices in the power saving state are returned to the normal operation state for the distributed processing, the power consumption by the portion (module) unnecessary for the distributed processing is wasted. In the following, an embodiment that suppresses wasteful power consumption due to parts (modules) unnecessary for distributed processing will be described in detail.

[Printer]
FIG. 3 is a diagram illustrating a configuration example of the printer 1000 according to the embodiment. The present embodiment can be applied to a network environment in which a plurality of MFPs (MFPs), copying machines, laser beams, and inkjet printers are connected. In the following, a color laser beam printer (a typical printer) Hereinafter, this will be described as an example. Further, the printer shown in FIG. 3 prints an image having a recording density of 600 dpi based on multi-value data in which the pixels of each color component are expressed in gradation by 8 bits.

  In FIG. 3, the printer 1000 receives and stores a print command including print data (character code, image data, PDL data, etc.) and a control code supplied from a host computer 200 connected to the outside, and receives the print command. According to the printing command, a character pattern, an image, and the like are formed, and a color visible image is formed on the recording paper. The formatter control unit 110 analyzes a print command supplied from the host computer and performs print image generation processing, and controls the entire printer 1000. In addition, the formatter control unit 110 is provided with a switch, an LCD display, and the like for inputting a user operation / instruction and notifying the user of the status of the printer 1000. Connected to the operation panel 120.

  The final print image generated by the formatter control unit 110 is read to the output control unit 130 as a video signal VDO. The output control unit 130 inputs status signals from various sensors (not shown) arranged in each unit of the printer 1000 and outputs control signals to the optical unit 140 and various drive system mechanism units to control the printing process. Execute.

  The leading end of the recording paper P supplied from the paper feeding cassette 161 is held by the gripper 154f and held on the outer periphery of the transfer drum 154. On the photosensitive drum 151 by the laser beam output from the optical unit 140, the electrostatic latent image of the image separated into four colors is yellow (Y), magenta (M), cyan (C) and black (Bk). Are formed in this order. The electrostatic latent image of each color is developed with toner by the corresponding developing device Dy, Dm, Dc or Dk in the development selection mechanism unit 152, and the toner image of the development result is superimposed and transferred to the recording paper P on the transfer drum 154, A multicolor image is formed on the recording paper P.

  Thereafter, the recording paper P is separated from the transfer drum 154 and conveyed to the fixing unit 155. Then, the recording paper P on which the toner image is fixed by heat and pressure by the fixing unit 155 is discharged from the paper discharge unit 159 to the paper discharge tray unit 160.

  Here, the developing devices Dy, Dm, Dc, and Dk of the respective colors have rotation support shafts at both ends, and are respectively held by the developing device selection mechanism unit 152 so as to be rotatable about the shafts. As a result, as shown in FIG. 3, each developing device can maintain its posture constant even when the developing device selection mechanism 152 rotates around the rotation shaft 152a in order to select the developing device. . After the selected developing device moves to the developing position, the selection mechanism holding frame 153 having the fulcrum 153b is pulled toward the photosensitive drum 151 by the solenoid 153a, and the developing device selection mechanism 152 moves toward the photosensitive drum 151. The development process is performed at.

  Also, the formatter control unit 110 expands the print command into bitmap data depending on the device, and the output control unit 130 reads the video signal VDO corresponding to the bitmap data from the formatter control unit 110. This video signal is input to the laser driver 141 to drive the semiconductor laser element. The laser light L output from the semiconductor laser element is on / off controlled according to the video signal VDO, and is further reflected by the polygon mirror 142 that rotates at high speed by the scanner motor 143, via the f-θ lens 144 and the reflecting mirror 145. Then, scanning exposure is performed on the photosensitive drum 151 uniformly charged to a predetermined polarity by the charger 156. As a result, an electrostatic latent image corresponding to the video signal VDO is formed on the photosensitive drum 151.

  Next, for example, the M-color electrostatic latent image is developed by the M-color developing device Dm, and the M-color first toner image is formed on the photosensitive drum 151. On the other hand, the recording paper P is supplied from the paper feeding cassette 161 at a predetermined timing, and a transfer bias voltage having a polarity opposite to that of the toner (for example, plus polarity) is applied to the transfer drum 154, so that the recording paper P is transferred to the transfer drum 154. The first toner image on the photosensitive drum 151 is transferred to the recording paper P while being electrostatically attracted to the surface. After the toner image is transferred, the toner remaining on the photosensitive drum 151 is removed by the cleaner 157 to prepare for the formation and development of the next color latent image.

  Thereafter, scanning exposure of the electrostatic latent images of the second, third and fourth colors, development and transfer of the toner image are performed in the order of C, Y and Bk by the same procedure. However, the second, third and fourth colors are different in that a higher bias voltage is applied to the transfer drum 154 than before.

  When the leading edge of the recording paper P onto which the four color toner images are superimposed and transferred approaches the separation position, the separation claw 158 approaches, and the leading edge of the separation claw 158 contacts the surface of the transfer drum 154, and the recording paper P is separated from the transfer drum 154. As described above, the separated recording paper P is conveyed to the fixing unit 155, and after the toner image on the recording paper is fixed, the recording paper P is discharged onto the paper discharge tray 160.

  The printer 1000 outputs an image at a resolution of 600 dpi through the image forming process as described above. The printer that can be used as the printing apparatus in this embodiment is not limited to a color laser beam printer, but may be a color printer of another type such as an ink jet printer or a thermal printer, or a monochrome printer.

[Printing system]
FIG. 4 is a block diagram illustrating a configuration example of a printing system according to the embodiment. The printing system has a configuration in which a host computer 3000 and a plurality of printers 1000, 1001, 1002,... Are connected to each other via a communication path 2000. . FIG. 4 shows three printing apparatuses, but the number of printing apparatuses is not limited.

● Formatter control unit The formatter control unit 110 is also called a PDL controller, etc., and is a network interface (I / F) 3101 that communicates with the host computer 3000, a reception buffer 3103 that temporarily stores received data, and transmission data The transmission buffer 3104 that temporarily stores, a command analysis unit 3107 that analyzes print data, a print control processing unit 3109 that executes print control processing, a drawing processing unit 3105 that executes drawing processing, a page memory 3106, and the like The

  The network I / F 3101 transmits / receives print data to / from the host computer 3000 or the like. However, the connection method between the host computer 3000 and the printing apparatus is arbitrary, and connection via a computer network such as a LAN or connection via a serial bus such as USB (Universal Serial Bus) or IEEE1394 may be used. Of course, infrared or wireless can be used as the communication path 2000.

  The print data received by the network I / F 3101 is sequentially stored in the reception buffer 3103, and is read and processed by the command analysis unit 3107 or the drawing processing unit 3105 as necessary. The command analysis unit 3107 is configured by a control program according to a print command system or a print job control language. When the command relates to drawing of character printing, graphics, images, etc., the command processing unit 3107 instructs the drawing processing unit 3105 to perform the processing, and the command Is other than drawing, such as paper feed selection or reset command, the process is instructed to the print control processing unit 3109.

  The drawing processing unit 3105 is a YMCK renderer that sequentially develops each drawing object of characters and images in a band memory in the page memory 3106. In the case of the color laser beam printer shown in FIG. 3, it is necessary to send device-dependent bitmap data to the printer engine 3110 in the order of MCYK. However, in the standard state, not all the memory capacity necessary for that is secured. In other words, the drawing processing unit 3105 secures a memory area having a capacity of a fraction of one plane (1, 2, or 4 bits / pixel) as a band memory in the page memory 3106, and repeatedly uses the band memory to A drawing process synchronized with the process of the engine 3110 is executed. The printer engine 3110 is a general term for the entire configuration for executing the above-described image forming process, such as the optical unit 140, the photosensitive drum 151, the development selection mechanism 152, the transfer drum 154, and the fixing unit 155 shown in FIG.

  Normally, the page memory 3106 is managed by banding control followed by the video signal shipping process to the printer engine 3110 for the development processing by the rendering processing unit 3105. However, if there is sufficient memory capacity, a bit map for one page is used. A memory area where data can be expanded may be secured.

  In general, the formatter control unit 110 causes a computer system using a central processing unit (CPU), read only memory (ROM), random access memory (RAM), etc. to execute a control / processing program for the formatter control unit. Consists of. The processing of each part in the formatter control unit 110 may be configured to be time-sharing based on a multitask monitor (real-time OS), or a dedicated controller hardware is prepared for each function independently. It may be a configuration to be processed.

  As described above, the operation panel 120 is for inputting a user operation / instruction and notifying the user of the status of the printer 1000. The output control unit 3108 converts the bitmap data expanded in the band memory (page memory) 3106 into a video signal, and transfers it to the printer engine 3110. The printer engine 3110 forms a visible image on the recording paper based on the received video signal.

Host Computer The host computer 3000 outputs print data composed of print data and control codes to the printer 1000. The host computer 3000 is configured as one computer system to which a keyboard 310 and a mouse 311 as input devices and a display monitor 320 as a display device are connected. The host computer 3000 includes hardware such as a central processing unit (CPU), read only memory (ROM), random access memory (RAM), hard disk drive (HDD), and various input / output control units (I / O). Basic software (OS) such as Windows (R) manages the control, and each application software and subsystem process operates as a functional module based on the basic software.

  Focusing only on the functions related to the present embodiment, the functional units of the host computer 3000 are divided into application software 301, a graphic subsystem 302, a spooler 303, and a network interface 3033 that communicates with the printing apparatus. The application software 301 is application software that creates a general document that runs on an OS such as a word processor or spreadsheet.

  The graphics subsystem 302 includes a graphics device interface (hereinafter referred to as “GDI”) 3021 which is a part of the OS function, a printer driver 3022 which is a device driver dynamically linked from the GDI 3021, a band spooler 3023, and accumulated data. 3024 (for example, both are stored in a predetermined area of the RAM). The printer driver 3022 is called from the GDI 3021 via the Device Driver Interface (hereinafter referred to as “DDI”) 3025, and performs processing corresponding to the printing apparatus for each drawing object. The host computer 3000 according to the present embodiment converts the information passed to the DDI function into a print command data (PDL) format that can be processed at high speed by the printer and directly sends it to the spooler 303, and the generated print command data. Are divided into band units, one page is sequentially stored in the band spooler 3023 from the first band, and the processes are collectively sent to the spooler 303 at the end of the page.

  The spooler 303 is a spool file system managed by the OS, and stores print data as a spool file 3031 (for example, a storage area is allocated to the HDD) according to settings in units of one page or job, and the I / F 3032 and the network I / F Send to printer via 3033.

  Although the names and functional frameworks of the above-described parts may differ slightly depending on the OS, differences in these names and frameworks do not affect the essence of the present embodiment. For example, a module called a spooler or a spool file in this embodiment can be realized using a module called a print queue in another OS.

Printer Driver Processing FIG. 5 is a diagram schematically showing the processing outline of the printer driver 3022. A document 4001 created using a general document creation application includes graphics, characters, and images.

  When printing the document 4001, first, drawing commands 4002 and 4003 are passed to the printer driver 3022 installed in the OS via the OS. In the initial state, the printer driver 3022 generates a print command (PDL) for each drawing command, writes it to the spooler 303, and uses a predetermined calculation formula corresponding to the number of commands and the type of command in the same manner as a normal PDL mode driver. The calculated data size is integrated as integrated data 3024 (S4004). The drawing command (DDI function) received by the printer driver 3022 via the OS is a specification that is output in order from the lower layer of the overlapping drawing objects. When all the data for one page has been written, the spooler 303 sends the print command (PDL) stored as the spool file 3031 and the accumulated data 3024 to the task manager described later, clears the spool file 3031, and stores the accumulated data 3024. Clearing is instructed to the printer driver 3023 (S4012).

  On the other hand, when the value of the accumulated data 3024 exceeds a predetermined data size, the number of commands, etc., the page unit processing is switched to the following band unit processing. Note that “rectangular drawing (image background)” 4021, “image drawing” 4022 and “image entity (image data)” 4023 shown in FIG. 5 are stored in the spooler 303, and “image entity” 4023 is stored in the spooler 303. It is assumed that the integrated data 3024 is switched to band-by-band processing at a timing when the accumulated data 3024 exceeds a predetermined data size threshold at the time when the data is output.

  When the printer driver 3022 switches to band-by-band processing at the above timing, the printer driver 3022 generates a print command for the rendering command 4003 after the “image entity” 4023, and divides the print command for each band area processed by the printing apparatus. It is stored and managed in the band spooler 3023 in the drawing order (S4006). Since the drawing command 4003 (DDI function) passed from the OS is output regardless of the printing direction of the printing apparatus, even when switching to band-by-band processing from the middle of the page as in this embodiment, the first Storage processing is performed for all the bands in the page from the band to the Nth band.

  The storing process is performed every time the DDI function in the printer driver 3022 is called. If the storage area reserved for processing in units of bands runs out of space, it is dealt with by securing a new RAM area. When storing the drawing data from the first band to the Nth band corresponding to the remainder of one page is completed, the data is written to the spooler 303 in the order of bands to be processed by the printing apparatus, and the band spooler 3023 is cleared ( S4009).

  By adding band data information (Band N inf) 4011 to be transmitted later to the head of each band data, the printing apparatus recognizes that the print data has shifted from page units to band units. When the print data for one page is written, the spooler 303 transmits a spooler file 3031 and accumulated data 3024 to a task manager described later, clears the spool file 3031, and instructs the printer driver 3022 to clear accumulated data 3024. (S4012).

FIG. 6 is a diagram illustrating a hardware configuration example of the printing apparatus.

  The CPU 501 of the printing apparatus performs control of the entire printing apparatus, arithmetic processing including image processing, and the like using the RAM 503 as a work memory in accordance with a control / processing program stored in the ROM 502. The ROM 502 stores a control / processing program and the like, and the CPU 501 operates by reading the program from the ROM 502 and executing it. The RAM 503 includes a reception buffer 3103 that temporarily stores data transmitted to and received from the network 2000, a transmission buffer 3104, a page memory 3106 that temporarily stores drawn image data, a work memory that temporarily stores data necessary for the CPU 501 to perform calculations, and the like. Used as By combining these CPU 501, ROM 502, and RAM 503, the format control unit 110 and the like are realized.

  The CPU 501, ROM 502, and RAM 503 are connected to each other via a system bus 504, and further connected to an expansion bus 505 via a bus bridge 506. With the bus bridge 506, the system bus 504 and the expansion bus 505 can operate independently. The printer I / F 507 transfers image data stored in the RAM 503 or the like to the printer engine 3110.

  The network I / F 3101 includes an IEEE1284 I / F 508 that is a bicentro interface and a network controller 509. The PHY 511 is a physical transceiver for connecting to the network 2000. The MII I / F 512 is an interface for connecting the LANC 509 to the PHY 511 and performs handshake data transfer with the PHY 511. Furthermore, the control unit 513 built in the LANC 509 performs control within the LANC 509 and control of communication with the outside. The control unit 513 can notify the CPU 501 of an interrupt through the dedicated signal line 510, and can notify the end of data transmission / reception with the network 2000. When a data packet is received from another device on the network 2000 and a specific bit pattern is detected from the data packet (hereinafter referred to as “receive a specific packet”), the CPU 501 is notified by an interrupt. . Note that the specific packet includes a magic packet and a packet indicating the start of distributed processing, which will be described later, and these bit patterns are held in the control unit 513 in advance. Note that a bit pattern of a packet indicating the start of distributed processing is set in advance between the host computer and the printing apparatus. In this embodiment, a packet having a specific bit pattern indicating the start of the distributed processing is referred to as a “Grid packet”.

  The clock control unit 514 distributes the clock to each of the modules via a clock supply line (not shown). The clock control unit 514 stops the clock supplied to some modules (hereinafter referred to as “clock stop”), cancels the clock stop, and supplies to some modules according to the value of the register 514a that can be set from the CPU 501. Control such as setting the clock to a frequency lower than that during normal operation (hereinafter referred to as “clock down”) and returning to the frequency during normal operation (hereinafter referred to as “clock up”) is possible.

Distributed Processing FIG. 7 is a diagram for explaining distributed processing of the printing system. In the following description, it is assumed that the task manager (TM) 3034 and the dynamic job scheduler (DJS) 3035 function by software installed on basic software executed by the CPU of the host computer 3000. The broker and resource manager (RM) function by software installed on basic software executed by the CPU of each printing apparatus.

  First, the host computer 3000 starts a job. In this embodiment, the job is a printing operation. Upon receipt of the job, the TM 3034 sends a job request to the DJS 3035 to request the analysis, and based on the analysis result from the DJS 3035 (including notification indicating the best broker), the job is sent to the broker 1003, 1005 and / or The job is input to 1007 (FIG. 7 shows a state where a job is input to the broker 1007 of the printer 1002). The DJS 3035 periodically inquires about the status of the broker, constantly grasps the status of resources (printing device availability) and the status of the entire printing system, and selects the optimum broker.

  The brokers 1003, 1005, and 1007 of each printing device take up resource availability from the RMs 1004, 1006, and 1008 of the same device, and register them in the DJS 3035. Also, when a broker submits a job from TM 3034, each broker searches for the optimal resource, submits the job to that resource via RM, and notifies TM 3034 of the job completion notification (and processing result) from RM. To do. Further, each RM notifies the broker of the same device if there is an abnormality in the resource. Note that an abnormality refers to a case where a job is submitted from another client and the job submitted / submitted from TM 3034 cannot be processed continuously.

  FIG. 8 is a flowchart showing the processing of TM 3034.

  The TM 3034 waits for the job to be submitted (S1101), and predicts the processing time when the job is submitted (S1102). The processing time can be predicted from the integrated data 3024 described above.

  Next, it is determined whether or not to perform distributed processing from the prediction result of processing time (S1103), and when it is determined that distributed processing is faster, processing divided from a job is input to a predesignated device (S1105). ). Note that the process division method may be a band unit, a page unit, or the like. Of course, processing divided into a plurality of devices may be distributed and a job may be submitted to the device if it is faster to process all of the devices.

  DJS 3035 periodically checks the status of resources (printing device availability information) etc. connected to the network in order to inquire the status of the broker 1007 etc. installed in the printer 1002 etc. connected to the network. This information is held internally. For this reason, when specifying a device, it is possible to select a free device based on the network resource information held by the DJS 3035 and submit a job.

  Next, the processing results (in this case, the image data that has been rendered and converted into bitmap data) returned from the device that has submitted the divided processing are combined (S1106), and the printer specified for the job is allowed to print the image. (S1107) to finish the job. Of course, when the entire job is submitted to one device, it is not necessary to combine the processing results.

  Also, in the determination in step S1103, it is expected that the processing specified by the printer designated for the job is faster, and the processing performed by the distributed processing is faster. If it is not possible, or if the job can be processed sufficiently at the processing speed of the printer specified relatively lightly, the processing (rendering and conversion to bitmap data) (S1104) and image printing ( S1107) is performed and the job is terminated.

  Here, it is assumed that division processing is input to the printer 1000 by the TM 3034. The broker 1003 operating on the CPU 501 of the printer 1000 responds to the distributed processing start instruction by the TM 3034, and then the RM 1004 operating similarly on the CPU 501 responds. Then, the broker 1003 returns to the TM 3034 that the division process can be received and the resource status of the printer 1000. In response to this reply, TM 3034 transmits a division process to the broker 1003.

  FIG. 9 is a flowchart for explaining control of power consumption of a device that has undergone division processing.

  The printer 1000 is in a standby state until the packet is received from the network 2000 (clock stop or power-down state where the clock is down). When the LAN controller (LANC) 509 receives the packet, it generates an interrupt and sends it to the CPU 501. The reception of the packet is notified (S701). The CPU 501 that has received the interrupt reads the value of the register 509a in the LANC 509, determines the cause of the interrupt (S702, S703), and in the case of an interrupt due to reception of a magic packet, the register 514a in the clock control unit 514 is read. By operating, the normal operation is started by releasing the clock stop and raising the clock (S704). In the case of an interrupt due to reception of a Grid packet (packet indicating the start of distributed processing), resources required for distributed processing (CPU 501, RAM 503, bus bridge 506, network I / F 3101, etc. in the example of FIG. 6) Only the clock stop is canceled and the clock is increased (S705), the data of the division processing sent from the TM 3034 is received, and the distributed processing is executed (S706).

  The LANC 509 sets a bit indicating the type of received packet (magic packet or Grid packet) in the register 509a indicating the internal interrupt factor. By reading the value of the register 509a, the CPU 501 can know whether the received packet is a magic packet, a Grid packet, or any other packet. If a packet other than the magic packet and the Grid packet is received, the printer 1000 does not perform any operation and ends the processing as it is.

  FIG. 15 is a flowchart for explaining the control of the power consumption of the device in consideration of the case where the interruption due to the Grid packet occurs in the processing shown in FIG. 9 and the magic packet is received before starting the distributed processing in step S706. is there.

  The CPU 501 releases the clock stop and clocks up only the resources necessary for distributed processing (S705), and then reads the value of the register 509a of the LANC 509 and determines whether a magic packet has been received (S711). If a magic packet has not been received, distributed processing (S706) is executed.If a magic packet has been received, the value in the non-volatile RAM (NVRAM) 503a is read and priority is given to print processing or priority is given to distributed processing. It is determined whether to do (S712). Note that which process is prioritized can be set from the operation panel 120, and the setting is held in the NVRAM 503a.

  If priority is given to print processing, the CPU 501 (broker 1003) notifies the TM 3034 of the suspension of distributed processing (S713), cancels clock stop and clocks up all resources, and executes print processing (S714). . Then, after the printing process is completed, the CPU 501 (broker 1003) notifies the TM 3034 of the restart of the distributed process (S715), and performs the distributed process by stopping or clocking down resources unnecessary for the distributed process ( S716). Note that if the cancellation of the distributed processing is notified from the TM 3034 after notifying the restart of the distributed processing, the CPU 501 does not execute the distributed processing.

  If priority is given to the distributed processing, the CPU 501 executes the distributed processing (S717), and then cancels the clock stop and clocks up all resources and executes the printing processing (S718).

  In this way, when a Grid packet is received, only the part required for distributed processing (in the example of FIG. 6, CPU 501, RAM 503, bus bridge 506, network I / F 3101, etc.) has a frequency clock during normal operation. The parts such as the printer I / F 507 and the printer engine 3110 that are not necessary for the distributed processing are stopped or clocked down. Therefore, it is possible to prevent the target device of the distributed processing from consuming unnecessary power in a portion unnecessary for the distributed processing during the distributed processing.

  In order to suppress power consumption, not only clock stop and clock down, but also power supplied to the module by the power control unit may be stopped. In that case, in step S705, the CPU 501 controls the power control unit so as to release the power stop to the modules necessary for the distributed processing.

  Hereinafter, Example 2 according to the present invention will be described. In Example 2, the same components as those in Example 1 are denoted by the same reference numerals, and detailed description thereof will be omitted.

  The second embodiment is different from the first embodiment in that a power control unit 516 that performs power control is added to the printer 1000 and a LANC 509 interrupt signal 515 when a packet is received from the network 2000 as shown in FIG. Is input to the power control unit 516. The power control unit 516 has a function of turning on / off the power supplied to modules other than the LANC 509, and can restart the supply of the stopped power when receiving the interrupt signal 515 from the LANC 509.

  Here, it is assumed that division processing is input to the printer 1000 by the TM 3034. Assume that the TM 3034 acquires resource information of the printer 1000 from the brokers 1003 and RM 1004 operating on the printer 1000 before the power control unit 516 causes the printer 1000 to transition to the power saving state.

  When the LANC 509 receives a packet from the network 2000, the LANC 509 generates an interrupt signal 515. Receiving the interrupt signal, the power control unit 516 resumes power supply to modules other than the LANC 509.

  FIG. 11 is a flowchart for explaining control of power consumption of a device that has undergone division processing.

  When the power supply is resumed, the CPU 501 executes a boot-up process (S801). The boot-up process is a process in which the CPU 501 reads a program stored at a predetermined address in the ROM 502 and executes initialization of each module in the printer 1000.

  When the bootup process ends, the CPU 501 reads the value of the register 509a in the LANC 509 and determines whether the received packet is a magic packet or a Grid packet (S802, S803). When the magic packet is received, it is assumed that the normal printing process is started, data is received from the host computer 3000 and the printing process is executed (S804). On the other hand, if a Grid packet is received, the resources other than those required for distributed processing (such as the printer I / F 507 and printer engine 3110 in the example of FIG. 6) are stopped or clocked down (S805), and sent from TM 3034. The division processing data received is received and distributed processing is executed (S806).

  In this way, when the Grid packet is received after the power supply is resumed, it is normal only for the parts necessary for distributed processing (CPU 501, RAM 503, bus bridge 506, network I / F 3101 etc. in the example of FIG. 6). A clock having a frequency at the time of operation is supplied, and parts such as the printer I / F 507 and the printer engine 3110 that are unnecessary for distributed processing are stopped or clocked down. Therefore, when performing distributed processing on the target device of distributed processing, it is possible to suppress power consumption of a portion unnecessary for distributed processing.

  Hereinafter, Example 3 according to the present invention will be described. In Example 3, components substantially the same as those in Examples 1 and 2 are denoted by the same reference numerals, and detailed description thereof will be omitted.

  The third embodiment is different from the first embodiment in that a hard disk interface (HD I / F) 517 and a hard disk drive (HDD) 518 are added to the printer 1000 as shown in FIG. The CPU 501 can read and write data between the RAM 503 and the HDD 518 by controlling the HD I / F 517.

  FIG. 13 is a flowchart for explaining control of power consumption of a device that has undergone division processing. Note that before the division process is input, the printer 1000 is supplied with power to each module in order to perform normal operation, and the clock controller 514 is supplied with a clock having a frequency during normal operation from each module.

  The CPU 501 determines whether an interrupt has occurred from the LANC 509 (S901). When the host computer 3000 transmits a Grid packet to the LANC 509 to execute distributed processing, the LANC 509 notifies the CPU 501 of reception of the packet by an interrupt signal 510. The CPU 501 that has detected the occurrence of the interrupt reads the value of the register 509a in the LANC 509 and determines whether or not a Grid packet has been received (S902). If the normal print processing is received from the host computer 3000 without receiving the Grid packet, the normal print processing is executed (S903).

  On the other hand, when receiving the Grid packet, the CPU 501 saves the print processing program and the like existing on the RAM 503 to the HDD 518 (S904). As shown in FIG. 14 (a), the RAM 503 holds a program area for a system including an OS, which is basic software, a program area for print processing for performing print processing, image data, and the like. There is a data area for print processing, etc., and in order to create an empty area on the RAM 503 when starting distributed processing, a program area for print processing, and if necessary, a data area for print processing are provided. Evacuate to HDD 518.

  Next, the CPU 501 downloads a program for distributed processing (S905). The distributed processing program is downloaded from the host computer 3000 via the network 2000 and expanded on the RAM 503, or the program stored in the HDD 518 in advance is read from the HDD 518 and expanded on the RAM 503. There is. FIG. 14 (b) is a diagram showing allocation of the RAM 503 after the distributed processing program is expanded, and a data area for distributed processing for holding the distributed processing result is also secured by the OS.

  Next, the CPU 501 sets the register 514a of the clock control unit 514 and, for example, a printer I / F 507, a printer other than resources (CPU 501, RAM 503, network I / F 3101, etc.) necessary for distributed processing The engine 3110 and HD I / F 517 are stopped or clocked down (S906). Of course, the rotation of the disk of the HDD 518 may be stopped.

  Next, the CPU 501 executes the dividing process input from the host computer 3000 (S907), and when the dividing process ends, controls the LANC 509 and transfers (uploads) the result of the dividing process to the host computer 3000 ( S908), canceling the clock stop and clocking up (S909). If the disk rotation of the HDD 518 is stopped, the rotation is resumed, and the print processing program area (and the data area for print processing if necessary) saved in the HDD 518 is restored to the RAM 503 ( S910), the distributed processing is terminated.

  In this way, when starting distributed processing, programs and data areas that are not involved in distributed processing on the RAM 503 are temporarily saved in the HDD 518 to secure an area in the RAM 503 that holds the distributed processing programs and data. . Accordingly, distributed processing can be performed even when the storage capacity of the relatively small RAM 503 is small, and furthermore, power consumption during distributed processing can be suppressed by stopping or clocking down modules that are not involved in distributed processing.

[Other embodiments]
Note that the present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, and a printer), and a device (for example, a copying machine and a facsimile device) including a single device. You may apply to.

  Also, an object of the present invention is to supply a storage medium (or recording medium) on which a program code of software that realizes the functions of the above-described embodiments is recorded to a system or apparatus, and the computer (or CPU or CPU) of the system or apparatus. Needless to say, this can also be achieved by the MPU) reading and executing the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention. Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an operating system (OS) running on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

  Furthermore, after the program code read from the storage medium is written into a memory provided in a function expansion card inserted into the computer or a function expansion unit connected to the computer, the function is determined based on the instruction of the program code. Needless to say, the CPU of the expansion card or the function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

  When the present invention is applied to the storage medium, the storage medium stores program codes corresponding to the flowcharts described above.

A diagram describing the architecture of grid computing, The figure explaining the example of composition in the case of applying the technology of desktop grid computing to printer description language (PDL) processing, The figure which shows the structural example of the printer of an Example. Block diagram showing a configuration example of a printing system of an embodiment The figure which shows the processing summary of the printer driver typically, The figure which shows the hardware structural example of a printing apparatus, A diagram for explaining distributed processing of a printing system, Flow chart showing TM processing, A flowchart illustrating control of power consumption of a device that has undergone division processing; FIG. 4 is a diagram illustrating a hardware configuration example of the printing apparatus according to the second embodiment. A flowchart for explaining control of power consumption of a device that has been subjected to the division processing of the second embodiment, The figure which shows the hardware structural example of the printing apparatus of Example 3, Flowchart explaining the control of power consumption of the device that has been subjected to the division processing of Example 3, Diagram showing RAM allocation, 10 is a flowchart for explaining control of power consumption of a device in consideration of a case where an interrupt due to a Grid packet occurs and a magic packet is received before starting distributed processing in the processing illustrated in FIG.

Claims (17)

An information processing apparatus connected to a computer network,
An information processing apparatus, wherein when a packet indicating distributed processing is received from a host machine via the computer network, only a resource necessary for the distributed processing is canceled and clocked up. An information processing apparatus connected to a computer network,
When a packet indicating distributed processing is received from a host machine via the computer network, supply of a clock to a resource unnecessary for the distributed processing is stopped, or a frequency of a clock to be supplied to the resource is set from a normal operation time. An information processing apparatus that is set to a low frequency. An information processing apparatus connected to a computer network,
When the information processing apparatus is not performing data processing, power suppression means for stopping power or clock supplied to some modules constituting the information processing apparatus or reducing the frequency of the clock;
Determining means for determining the type of packet received from a host machine via the computer network;
When the determination result indicates reception of a packet indicating the start of distributed processing, the power or clock supplied to the module required for the distributed processing is stopped, and control means for canceling the reduction of the clock frequency An information processing apparatus comprising:   The control means cancels the stop of the power or clock and the reduction of the frequency of the clock by the power control means when the determination result indicates reception of a packet indicating the start of printing processing. The information processing apparatus according to claim 3. And holding means for holding setting information indicating which of the distributed processing and the print processing is preferentially processed,
When the packet indicating the start of the printing process is received before the start of the distributed process after the packet indicating the start of the distributed process is received, the control unit, based on the setting information, 5. The information processing apparatus according to claim 4, wherein the printing process is preferentially processed.   6. The information processing apparatus according to claim 3, wherein the modules necessary for the distributed processing include at least a CPU, a memory, and a network interface.   The determination means includes a register accessible from the control means for storing a result of determining the type of the packet, and a notification means for transmitting a signal indicating reception of the packet to the control means. An information processing apparatus according to any one of claims 3 to 6.   7. The register according to claim 3, wherein the power suppression unit includes a register accessible from the control unit, which sets the stop of the power or clock and the reduction of the frequency of the clock. Information processing apparatus described in 1.   9. The information processing apparatus according to claim 3, further comprising transmission means for transmitting the result of the distributed processing to the host machine via the computer network. An information processing apparatus connected to a computer network,
Receiving means for receiving a packet from a host machine via the computer network;
When the information processing apparatus is not performing data processing, power to stop power supply to some modules constituting the information processing apparatus and release the power supply stop when the receiving unit receives a packet Suppression means;
A clock control means for stopping a clock supplied to some of the modules constituting the information processing apparatus or reducing the frequency of the clock;
The type of packet received by the receiving unit is determined, and when the packet indicates the start of distributed processing, the clock supplied to the module unnecessary for the distributed processing is stopped to the clock control unit, or the frequency of the clock is An information processing apparatus having control means for reducing the information processing apparatus. An information processing apparatus connected to a computer network,
Saving / restoring means for saving data in an area allocated to the memory to a storage device and returning the data saved to the storage device to the memory;
A clock control means for stopping a clock supplied to some of the modules constituting the information processing apparatus or reducing the frequency of the clock;
Determining means for determining the type of packet received from a host machine via the computer network;
If the determination result indicates reception of a packet indicating the start of distributed processing, the save / restore means saves data in a predetermined area on the memory and supplies the clock control means to a module unnecessary for the distributed processing. An information processing apparatus comprising: control means for stopping a clock or reducing a frequency of the clock. Furthermore, it has a transmission means for transmitting the result of the distributed processing to the host machine via the computer network,
The control means causes the clock control means to cancel the stop of the clock and the frequency reduction of the clock after transmitting the distributed processing result, and the data saved in the storage device by the save / restore means is stored in the memory. 12. The information processing apparatus according to claim 11, wherein the information processing apparatus is restored. A power suppression unit that is connected to a computer network and stops power or clock supplied to some of the modules constituting the device or reduces the frequency of the clock when the device is not processing data; A method for controlling an information processing apparatus,
Determining the type of packet received from the host machine via the computer network;
When the result of the determination indicates reception of a packet indicating the start of distributed processing, the stop of the power or clock supplied to the modules necessary for the distributed processing and the reduction of the frequency of the clock are released. Control method to do. Stops power supply to a receiving unit that is connected to a computer network and receives packets from a host machine via the computer network, and to some modules that constitute the device when the device is not processing data And a control method of an information processing apparatus having a power suppressing unit that cancels the stop of the power supply when the receiving unit receives a packet,
Determine the type of packet received by the receiver,
When the packet indicates the start of distributed processing, a clock supplied to a module unnecessary for the distributed processing is stopped or the frequency of the clock is reduced. A method for controlling an information processing apparatus connected to a computer network, comprising:
Determining the type of packet received from the host machine via the computer network;
When the determination result indicates reception of a packet indicating the start of distributed processing, data in a predetermined area on the memory is saved to a storage device, and a clock supplied to a module unnecessary for the distributed processing is stopped, or the clock The control method characterized by reducing the frequency of the.   16. A program that controls an information processing apparatus to realize the control according to any one of claims 13 to 15.   17. A recording medium on which the program according to claim 16 is recorded.

Images